Scholarly Contributions

Academic Publications

Explore peer-reviewed articles, books, conference proceedings, and groundbreaking research published by Mountain Top University faculty members.

πŸ“š Total: 187 Academic Publications
πŸ‘οΈ Summation: 120,940 Article Clicks & Reads
πŸ” Staff Sign In to Add Multiple Publications or Update
πŸ” βœ•
Showing publications matching "Studies" (187 results)
βœ• Clear Filter View Authors in Staff Directory β†—
Popular Academic Themes & Topics
Nigeria 460 State 140 Effect 130 Nigerian 126 Lagos 114 Selected 98 Properties 93 Quality 90 Performance 87 Development 85 Management 80 State Nigeria 79 Studies 75 Rats 75 Economic 73 Evaluation 67 Induced 60 Among 59 Flour 57 Fixed 56 Growth 56 African 55 Chemical 52 Extract 52 Corporate 52 Nutritional 51 Comparative 49 Production 49 Food 48 Aqueous 48 Financial 46 Lagos State 46 Waste 45 Social 45 Leaf 45
Cards View Table View
Sort By: πŸ“… Newest (Year) πŸ“ˆ Most Read (Clicks)

Enhancing Face Spoofing Attack Detection: Performance Evaluation of a VGG-19 CNN Model

2023
Dr. Thomas Gbadebo Ayanwola Dr. Thomas Gbadebo Ayanwola Lecturer II πŸ›οΈ Computer Science and Mathematics
πŸ“– Acadlore Transactions on AI and Machine Learning
Read Abstract

With the wide use of facial verification and authentication systems, the performance evaluation of Spoofing Attack Detection (SAD) module in the systems is important, because poor performance leads to successful face spoofing attacks. PreviousstudiesonfaceSADusedapretrainedVisualGeometryGroup(VGG)-16architecture to extract feature maps from face images using the convolutional layers, and trained a face SAD model to classify real and fake face images, obtaining poor performance for unseen face images. Therefore, this study aimed to evaluate the performance of VGG-19 face SAD model. Experimental approach was used to build the model. VGG-19 algorithm was used to extract Red Green Blue (RGB) and deep neural network features from the face datasets. Evaluation results showed that the performance of the VGG-19 face SAD model improved by 6% compared with the state-of-the-art approaches, with the lowest equal error rate (EER) of 0.4%. In addition, the model had strong generalization ability in top-1 accuracy, threshold operation, quality test, fake face test, equal error rate, and overall test standard evaluation metrics

View Article β†— πŸ‘οΈ 89 clicks Details β†’
1 2 3 4 5 6 7 8 9 10